AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism

Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon

ICML 2026 · Reinforcement learning › Offline RL · approach: Offline RL sample complexity theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adaptive uncertainty-based truncation with quantile 1.0 instead of 0.9 (ablation)NeuBay · D4RL locomotion (12 tasks)average normalized score: 22.5 -> 80.1Improved
use truncation quantile 1.0 instead of 0.99 (ablation)NeuBay · D4RL locomotion (12 tasks)average normalized score: 45.1 -> 80.1Improved
use truncation quantile 1.0 instead of 0.999 (ablation)NeuBay · NeoRL locomotion (9 tasks)average normalized score: 58.8 -> 64.7Improved
increase ensemble size from 5 to 100 (ablation)NeuBay · D4RL locomotion (12 tasks)average normalized score: 65.9 -> 80.1Improved
add strong uncertainty penalty (lambda 5.0) to NeuBay (ablation)NeuBay · D4RL locomotion (12 tasks)average normalized score: 80.1 -> 57.4Hurt
add small uncertainty penalty (lambda 0.04) to NeuBay (ablation)NeuBay · D4RL locomotion (12 tasks)average normalized score: 80.1 -> 79.8No clear effect
add uncertainty penalty to NeuBay (dataset-tuned lambda) (ablation)NeuBay · hopper-random-v2normalized score: 24.5 -> 48.2Improved
add uncertainty penalty to NeuBay (dataset-tuned lambda) (ablation)NeuBay · hopper-medium-v2normalized score: 54.2 -> 105.8Improved
add uncertainty penalty to NeuBay (ablation)NeuBay · AntMazenormalized scoreHurt
use history-dependent agent instead of Markov agent (ablation)NeuBay · D4RL Adroit (3 non-zero tasks)average normalized score: 36.4 -> 42.2Improved
use history-dependent agent instead of Markov agent (ablation)NeuBay · NeoRL locomotion (9 tasks)average normalized score: 64.7 -> 66.8 (Markov better)Hurt
add layer normalization to the world model (ablation)NeuBay world model · halfcheetah-medium-expert-v2compounding error / predicted state normImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy